AI Backend Engineer
San Francisco (HQ) • FullTime
Posted 5mo ago
About the job
We are seeking Backend + Applied AI Engineers to construct the core systems that power Within's multimodal agents in real enterprise environments. This is a hands-on role at the intersection of distributed systems and applied AI, where you will design and ship backend services for ingesting real-world data, orchestrating model/agent workflows, enforcing enterprise-grade security, and delivering reliable outcomes at scale. You will collaborate closely with product, design, and other engineers to transform ambitious AI capabilities into production-grade features for Fortune 500 enterprises. We prioritize strong engineering fundamentals, including correctness, observability, security, and performance, alongside rapid iteration speed, recognizing that success in this field depends on delivering quality products and features with incredible velocity.
Responsibilities
- Design, build, test, and deploy backend services that power the AI platform, handling data ingestion, storage, API design, background processing, and deployment architecture.
- Implement AI orchestration pipelines to ensure reliability under real-world variability, focusing on structured outputs, tool calling, state management, grounding, and other guardrails for scalable agent behavior.
- Develop and extend evaluation frameworks, add guardrails, and harden existing pipelines, rapidly gaining the judgment to design new ones.
- Balance long-term architectural vision with a consistent shipping cadence, making pragmatic decisions to maintain codebase health and product momentum.
- Design for enterprise security and scale, implementing least-privilege access, strong tenant isolation, auditability, and secure data handling, treating trust and safety as core engineering requirements.
Requirements
- 1-3 years of experience shipping production code, or exceptional new graduates with strong portfolios.
- Backend engineering skills with a focus on designing and building reliable, observable, secure, and fast services, APIs, data models, and infrastructure.
- Strong systems thinking ability to anticipate service evolution and design for the future while building for the present.
- Experience building AI-powered projects (production, open-source, or side projects) and understanding the difference between a demo and a reliable system.
- Proficiency in AI-native development across the SDLC, leveraging AI tools for technical design, API scaffolding, schema drafting, test writing, and migration planning.
- Ability to ship with velocity and craft, balancing speed with attention to detail and understanding the trade-offs between speed and technical debt.
- Demonstrated ability to bring energy that elevates the entire team, tackling distributed systems challenges with optimism and passion for craft.
- No CS or Engineering degree required; focus is on ability to ship, systems thinking, and evidence of strong execution.